LLM Alignment

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

48 papers in the last four weeks, up 118% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 422

All topics

Predicting Alignment Generalization with Value Representations
Oct 8, 2026Andy Liu, Mehar Bhatia, Karolina Stanczak +3LLM Alignment Representation Geometry in Language Models
Carnegie Mellon University · Mila - Quebec AI Institute · McGill University +4
Conversational Voice Aesthetic Model with Reinforcement Learning from Human Listeners
Oct 7, 2026Xilin Jiang, Shun Zhang, Tejas Jayashankar +2Speech Language Models LLM Alignment
Columbia University New York, NY, USA · Meta Superintelligence Labs Menlo Park, CA, USA
SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models
Oct 7, 2026Miao Yu, Hao Huang, Lu Yuan +3LLM Safety Alignment LLM Alignment
The University of Hong Kong (HKU) · Chinese Academy of Sciences (CAS) · Information Engineering University (IEU) +1
The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMs
Oct 7, 2026Jiachen Zhao, Zhengxuan Wu, David Bau +1LLM Fine-Tuning LLM Alignment
Northeastern University · Stanford University
Toward Alignment Scaling Laws: A Framework and First Preregistered Measurements
Oct 6, 2026Jeremy CanaleLLM Alignment Language Model Safety Evaluation
Reward Stealing Attack on Large Language Models
Oct 5, 2026Jiaming Qian, Pengyang Zhou, Jiahe Xu +1LLM Alignment Model Extraction Attacks
Zhejiang University
EmoRSS: Mitigating Emotion-Induced Over-Refusal in Large Language Models
Oct 4, 2026Shuyi Miao, Yaojin Ma, Chenhang Cui +5LLM Alignment LLM Refusal Behavior
Beihang University · University of Science and Technology Beijing · National University of Singapore +2
Detecting Inconsistencies in Model Specifications with LLM-as-Verifier Reasoning
Oct 1, 2026Zichen Xie, Mrigank Pawagi, Lize Shao +2LLM Alignment LLM Auditing
University of Virginia · University of Pennsylvania · The University of Texas at Austin
The Asymptotics of Language Model Alignment with Memory
Oct 1, 2026Haricharan Balasundaram, V. Arvind RameshwarRL for Language Models LLM Alignment
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA · IIT Madras · Department of Electrical Engineering, IIT Madras, Chennai, India
Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models
Oct 1, 2026Tido Specht, Elias Benedict Krey, Nils Neukirch +1LLM Alignment LLM Interpretability
University of Groningen · Carl von Ossietzky University of Oldenburg
GAW-PO: Preference Optimization with Gradient-Aligned Token Weights
Oct 1, 2026Andreea Dutulescu, Stefan Ruseti, Mihai Masala +2LLM Alignment Direct Preference Optimization
National University of Science and Technology POLITEHNICA Bucharest · NVIDIA
Pre-training interventions, ex post facto: Grafting model beliefs across checkpoints
Sep 30, 2026Peter Nutter, Dani Roytburg, Clément Dumas +2Fine-Tuning LLM Alignment
ETH Zurich · MATS · Carnegie Mellon University +2
Robust Nash Alignment under Preference Uncertainty
Sep 30, 2026Shihab Ahmed, Debamita Ghosh, David Tang +3LLM Alignment Preference Alignment
University of Central Florida · Arizona State University · University of Colorado Boulder
Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness
Sep 30, 2026Pardis Sadat Zahraei, Janvijay Singh, Gokhan Tur +1LLM Alignment Instruction Following
University of Illinois Urbana-Champaign
Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering
Sep 30, 2026Jiale Dai, Hongcan Deng, Liuxian Ma +2Disentangled Representation Learning LLM Alignment
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · University of Chinese Academy of Sciences · College of Artificial Intelligence, Tsinghua University
Ready2Blend: From Natural-Language Instructions to Composable Alignment Prompts
Sep 30, 2026Jeesu Jung, Hwan Chang, Juseon Do +5Continual Learning for LLMs LLM Alignment
Korea Advanced Institute of Science and Technology · Samsung SDS
Multi-LLM Collaborative Alignment via Stackelberg Games
Sep 30, 2026Christina Hahn, Shangbin Feng, Dean Light +3RL for Language Models LLM Alignment
University of Washington · Amazon · University of British Columbia
Optimal Design for Active Preference Learning with Biased LLM Judges
Sep 30, 2026Zhongman Du, Huiming Zhang, Haodong Zhu +1Pairwise Preference Learning LLM Alignment
Beihang University · Zhongguancun Academy · Hangzhou Innovation Institute of Beihang University
Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent
Sep 29, 2026Zheyuan Zhang, Mengyuan Chao, Ke Xiao +5LLM Alignment LLM Agent Evaluation
ByteDance Inc., USA · University of Notre Dame
Aligned Data Can Induce Misalignment via Context Confusion
Sep 29, 2026Yavuz Bakman, Duygu Nur Yaldiz, Baris Askin +4LLM Alignment LLM Post-Training
University of Southern California · Carnegie Mellon University · Amazon +1
The Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment
Sep 29, 2026Gonçalo Paulo, Louis Jaburi, Nora Belrose +2LLM Alignment LLM Fine-Tuning
EleutherAI
Correct, Don't Delete: Mitigating Emergent Misalignment with Corrective Supervision
Sep 29, 2026Jacob EpifanoLLM Alignment Emergent Misalignment in Language Models
Independent researcher
ContextAdapt: Evaluating Contextual Adaptation and Value Alignment in LLMs
Sep 29, 2026Olivia Macmillan-Scott, Mirco MusolesiLLM Alignment Language Model Safety Evaluation
Centre for AI, Department of Computer Science, University College London · Department of Computer Science and Engineering, University of Bologna
FLOORA: A Human-Aligned Domain-Specific Language Model for Architectural Design
Sep 28, 2026Sahand Rezaei-Shoshtari, Patryk Wozniczka, Shu Ishida +14LLM Alignment Language Modeling
Autodesk Research
From Normative Frameworks to Alignment Data: Constructing and Evaluating SFT and Preference Data
Sep 28, 2026Husrev Taha Sencar, Rezart Beka, Danish Naeem +6LLM Alignment Preference Alignment
Qatar Computing Research Institute, HBKU, Qatar. · College of Islamic Studies, HBKU, Qatar. · Argumentation and Conflict Studies, Ibn Haldun University, Turkiye. +1
BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment
Sep 28, 2026Antonio Ferrara, Alberto Rumi, Francesco BonchiLLM Alignment Debiased ML
Intesa Sanpaolo AI Research
ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control
Sep 28, 2026Eric Frankel, Banghua Zhu, Sewoong Oh +1RL for Language Models LLM Alignment
University of Washington, Seattle
When Do Agents Help? Embedding, LLM and Agentic Alignment of Classical Texts and Their Translations
Sep 27, 2026Máté MetzgerLLM Alignment LLM Agent Evaluation
Independent Researcher
Direct Hidden-State Alignment: Mapping and Controlling Preference Expression in LLMs
Sep 27, 2026Fansheng Zhang, Shengran Guo, Zexiao Wang +3LLM Alignment Preference Alignment
Chengdu University · North Carolina State University · Fudan University +2
Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
Sep 24, 2026Ruoqi Guo, Yi Liu, Gelei Deng +6LLM Safety Benchmarks LLM Alignment
Griffith University · Nanyang Technological University · UNSW +4

Oct 8, 2026, cs.CLJ/K move · Enter open · S save

Predicting Alignment Generalization with Value Representations

Andy Liu, Mehar Bhatia, Karolina Stanczak, Mona Diab+2

Carnegie Mellon University · Mila - Quebec AI Institute · McGill University+4

LLM Alignment Representation Geometry in Language Models

Open paper AskPDF arXiv

LLM developers post-train their models to exhibit prosocial values and behavioral traits, which are enumerated in an alignment target. However, while recent post-training developments have yielded models that score highly on alignment evaluations, training models on sets of narrow behaviors still influences their behavior across unseen contexts and environments in unexpected ways. In this paper, we establish the task of alignment generalization prediction, i.e., predicting how fine-tuning a model to follow a given value changes its behavior across a wide range of held-out values. We conduct a large-scale analysis of alignment generalization effects across 66 values found in modern alignment targets, and benchmark representational techniques on the alignment generalization prediction task. We find that representations based on model activations when applying values in context significantly outperform methods based on textual descriptions of the values. Specifically, the best activations-based methods achieve correlations of 0.45 with our generalization matrix, compared with 0.05 from description-based baselines. We then show the applicability of representations that predict alignment generalization toward downstream tasks by using them to measure how similar the values in a multi-value alignment target are, which we find is significantly correlated with model robustness. Finally, we show initial evidence towards a shared, model-independent value space, which we use to develop the first taxonomy of LLM values grounded in empirical generalization dynamics. Our work demonstrates the importance of studying value generalization in LLMs and its application toward the more empirical design and training of model behavior.

Momentum

Related topics

Latest papers 422